Differences across herds with different dairy breeds in daily milk yield based proxies for resilience.

Global sustainability issues such as climate change, biodiversity loss and food security require food systems to become more resource efficient and better embedded in the local environment. This needs a transition towards more diverse, circular and low-input dairy farming systems with animals best suited to the specific environmental conditions. When varying environmental challenges are posed to animals, cows need to become resilient to disturbances they face. This resilience of dairy cows for disturbances can be quantified using sensor features and resilience indicators derived from daily milk yield records. The aim of this study was to explore milk yield based sensor features and resilience indicators for different cattle groups according to their breeds and herds. To this end, we calculated 40 different features to describe the dynamics and variability in milk production of first parity dairy cows. After correction for milk production level, we found that various aspects of the milk yield dynamics, milk yield variability and perturbation characteristics indeed differed across herds and breeds. On farms with a lower breed proportion of Holstein Friesian across cows, there was more variability in the milk yield, but perturbations were less severe upon critical disturbances. Non-Holstein Friesian breeds had a more stable milk production with less (severe) perturbations. These differences can be attributed to differences in genetics, environments, or both. This study demonstrates the potential to use milk yield sensor features and resilience indicators as a tool to quantify how cows cope with more dynamic production conditions and select animals for features that best suit a farms' breeding goal and specific environment.

Early locomotor activity in broilers and the relationship with body weight gain.

Fast-growing broilers are relatively inactive and this is thought to be a result of selection for high growth rates. This reduced activity level is considered a major cause of leg weakness and associated leg health problems. Increased activity, especially early in life, is suggested to have positive effects on leg health, but the relationship between early activity and growth is unclear. A clearer understanding of the relationship between activity early in life and body weight gain could help determine how selecting on increased early activity could affect body weight gain in broilers. Here, a radio frequency identification (RFID) tracking system was implemented to record daily individual broiler activity throughout life, in 5 production rounds. As mean activity levels alone do not capture the variation in activity over time, multiple (dynamic) descriptors of activity were determined based on the individual birds' daily distances moved, focusing on the period from 0 to 15 days old. The mean, skewness, root mean square error (RMSE), autocorrelation, and entropy of (deviations in) activity were determined at the individual level, as well as the average daily gain (ADG). Relationships between activity descriptors and ADG were determined for 318 birds. Both when combining the data from the different production rounds and when taking production round and start weight into account, a negative relationship between ADG and RMSE was observed, indicating that birds that were more variable in their activity levels had a lower ADG. However, the activity descriptors, in combination with recording round and start weight, explained only a small part (8%) of the variation in ADG. Therefore, it is recommended for future research to also record other factors affecting ADG (e.g., type of feed provided and feed intake) and to model growth curves. Overall, this study suggests that increasing early activity does not necessarily negatively affect body weight gain. This could contribute to improved broiler health and welfare if selecting for increased activity has the expected positive effects on leg health.

Correlations of feed intake predicted with milk infrared spectra and breeding values in the Dutch Holstein population.

Feed is a major cost in dairy production, and substantial genetic variation in feed efficiency exists between cows. Therefore, breeders aim to improve feed efficiency of dairy cattle. However, phenotypic data on individual feed intake on commercial farms is scarce, and accurate measurements are very costly. Several studies have shown that information from Fourier-transformed infrared spectra of milk samples (milk infrared, milk IR) can be used to predict phenotypes such as energy balance and energy intake, but this is usually based on small data sets obtained under experimental circumstances. The added value of information from milk IR spectra for estimation of breeding values is unknown. The objectives of this study were (1) to develop prediction equations for dry matter intake (DMI) and residual DMI (rDMI) from milk IR spectra; (2) to apply these for a data set of milk IR spectra from commercial Dutch dairy farms; (3) to estimate genetic parameters for these traits; and (4) to estimate correlations between these predictions and other traits in the breeding goal. We used data from feeding trials where individual feed intake was recorded daily and for which milk IR spectra were determined weekly to develop prediction equations for DMI and rDMI with partial least squares regression. This data set contained over 7,600 weekly averaged DMI records linked with milk IR spectra from 271 cows. The equations were applied for a data set with test day information from 676 Dutch dairy herds with 621,567 records of 78,488 cows. Both milk IR-predicted DMI and rDMI were analyzed with an animal model to obtain genetic parameters and sire effect estimates that could be correlated with breeding values. A partial least squares regression model with 10 components from the milk IR spectra explained around 25% of DMI variation and less than 10% of rDMI variation in the validation set. Nearly all variation in the milk IR spectra was captured by 7 components; additional components contributed marginally to the spectral variation but decreased prediction errors for both traits. Accuracies of predictions of DMI and rDMI from milk IR spectra for a large feeding experiment were 0.47 and 0.26 on average, respectively, with small differences between ration treatments (ranging from 0.43 to 0.55 and from 0.21 to 0.34, respectively) and among lactation stages (ranging from 0.24 to 0.59 and from 0.13 to 0.36, respectively), with the highest prediction accuracies in early lactation. The estimated heritabilities for predicted DMI and rDMI were 0.3 and 0.4, respectively, which suggests genetic potential for both predicted traits. The correlations of sire estimates for milk IR-predicted DMI with official Dutch breeding values were strongest with milk production (0.33), longevity (0.26), and fertility (-0.27), indicating that cows that eat more produce more, live longer, and have poorer fertility. The correlations of sire estimates for predicted DMI and rDMI with the official breeding values for DMI were low (0.14 and 0.03, respectively). This implies that the added value of including milk IR-predicted DMI information in the estimation procedure of breeding values for DMI would be considered insufficient for practical application.

Integrating heterogeneous across-country data for proxy-based random forest prediction of enteric methane in dairy cattle.

Direct measurements of methane (CH4) from individual animals are difficult and expensive. Predictions based on proxies for CH4 are a viable alternative. Most prediction models are based on multiple linear regressions (MLR) and predictor variables that are not routinely available in commercial farms, such as dry matter intake (DMI) and diet composition. The use of machine learning (ML) algorithms to predict CH4 emissions from across-country heterogeneous data sets has not been reported. The objectives were to compare performances of ML ensemble algorithm random forest (RF) and MLR models in predicting CH4 emissions from proxies in dairy cows, and assess effects of imputing missing data points on prediction accuracy. Data on CH4 emissions and proxies for CH4 from 20 herds were provided by 10 countries. The integrated data set contained 43,519 records from 3,483 cows, with 18.7% missing data points imputed using k-nearest neighbor imputation. Three data sets were created, 3k (no missing records), 21k (missing DMI imputed from milk, fat, protein, body weight), and 41k (missing DMI, milk fat, and protein records imputed). These data sets were used to test scenarios (with or without DMI, imputed vs. nonimputed DMI, milk fat, and protein), and prediction models (RF vs. MLR). Model predictive ability was evaluated within and between herds through 10-fold cross-validation. Prediction accuracy was measured as correlation between observed and predicted CH4, root mean squared error (RMSE) and mean normalized discounted cumulative gain (NDCG). Inclusion of DMI in the model improved within and between-herd prediction accuracy to 0.77 (RMSE = 23.3%) and 0.58 (RMSE = 31.9%) in RF and to 0.50 (RMSE = 0.327) and 0.13 (RMSE = 42.71) in MLR, respectively than when DMI was not included in the predictive model. When missing DMI records were imputed, within and between-herd accuracy increased to 0.84 (RMSE = 18.5%) and 0.63 (RMSE = 29.9%), respectively. In all scenarios, RF models out-performed MLR models. Results suggest routinely measured variables from dairy farms can be used in developing globally robust prediction models for CH4 if coupled with state-of-the-art techniques for imputation and advanced ML algorithms for predictive modeling.

A data-driven prediction of lifetime resilience of dairy cows using commercial sensor data collected during first lactation.

Reliable prediction of lifetime resilience early in life can contribute to improved management decisions of dairy farmers. Several studies have shown that time series sensor data can be used to predict lifetime resilience rankings. However, such predictions generally require the translation of sensor data into biologically meaningful sensor features, which involve proper feature definitions and a lot of preprocessing. The objective of this study was to investigate the hypothesis that data-driven random forest algorithms can equal or improve the prediction of lifetime resilience scores compared with ordinal logistic regression, and that these algorithms require considerably less effort for data preprocessing. We studied this by developing prediction models that forecast lifetime resilience of a cow early in her productive life using sensor data from the first lactation. We used an existing data set from a Dutch experimental herd, with data of culled cows for which birth dates, insemination dates, calving dates, culling dates, and health treatments were available to calculate lifetime resilience scores. Moreover, 4 types of first-lactation sensor data, converted to daily aggregated values, were available: milk yield, body weight, activity, and rumination. For each sensor, 14 sensor features were calculated, of which part were based on absolute daily values and part on relative to herd average values. First, we predicted lifetime resilience rank with stepwise logistic regression using sensor features as predictors and a P-value of <0.2 as the cut-off. Next, we applied a random forest with the 6 features that remained in the final logistic regression model. We then applied a random forest with all sensor features, and finally applied a random forest with daily aggregated values as features. All models were validated with stratified 10-fold cross-validation with 90% of the records in the training set and 10% in the validation set. Model performances expressed in percentage of correctly classified cows (accuracy) and percentage of cows being critically misclassified (i.e., high as low and vice versa) ± standard deviation were 45.1 ± 8.1% and 10.8% with the ordinal logistic regression model, 45.7 ± 8.4% and 16.0% with the random forest using the same 6 features as the logistic regression model, 48.4 ± 6.7% and 10.0% for the random forest with all sensor features, and 50.5 ± 6.3% and 8.4% for the random forest with daily sensor values. This random forest also revealed that data collected in early and late stages of first lactation seem to be of particular importance in the prediction compared with that in mid lactation. Accuracies of the models were not significantly different, but the percentage of critically misclassified cows was significantly higher for the second model than for the other models. We concluded that a data-driven random forest algorithm with daily aggregated sensor data as input can be used for the prediction of lifetime resilience classification with an overall accuracy of ~50%, and provides at least as good prediction as models with sensor features as input.

Adaptation of Livestock to New Diets Using Feed Components without Competition with Human Edible Protein Sources-A Review of the Possibilities and Recommendations.

Livestock feed encompasses both human edible and human inedible components. Human edible feed components may become less available for livestock. Especially for proteins, this calls for action. This review focuses on using alternative protein sources in feed and protein efficiency, the expected problems, and how these problems could be solved. Breeding for higher protein efficiency leading to less use of the protein sources may be one strategy. Replacing (part of) the human edible feed components with human inedible components may be another strategy, which could be combined with breeding for livestock that can efficiently digest novel protein feed sources. The potential use of novel protein sources is discussed. We discuss the present knowledge on novel protein sources, including the consequences for animal performance and production costs, and make recommendations for the use and optimization of novel protein sources (1) to improve our knowledge on the inclusion of human inedible protein into the diet of livestock, (2) because cooperation between animal breeders and nutritionists is needed to share knowledge and combine expertise, and (3) to investigate the effect of animal-specific digestibility of protein sources for selective breeding for each protein source and for precision feeding. Nutrigenetics and nutrigenomics will be important tools.

The relationship between gait and automated recordings of individual broiler activity levels.

Gait, or walking ability, is an often-measured trait in broilers. Individual gait scores are generally determined manually, which can be time-consuming and subjective. Automated methods of scoring gait are available, but are often implemented at the group level. However, there is an interest in automated methods of scoring gait at the individual level. We hypothesized that locomotor activity could serve as a proxy for gait of individual broilers. Locomotor activity of 137 group-housed broilers from four crosses was recorded from approximately 16 to 32 days old, using an ultra-wideband tracking system. These birds were divided over four trials. Individual gait scores were determined at the end of the tracking period, on a scale from 0 to 5, with higher scores representing worse gait. Given the limited number of birds, birds were subsequently categorized as having a good gait (GG; scores 0-2) or a suboptimal gait (SG; scores 3-5). Relationships between activity and gait classification were studied to determine whether individual activity has the potential to serve as a proxy for gait. When comparing GG and SG birds using robust linear regression, SG birds showed a lower 1) activity around the start of tracking (estimate = -1.33 ± 0.56, P = 0.019), 2) activity near the end of tracking (estimate = -1.63 ± 0.38, P < 0.001), and 3) average activity (estimate = -1.12 ± 0.41, P = 0.007). When taking day of tracking, trial, cross and body weight category (heavy versus light at approximately 2 wk old) into account, a tendency was still observed for SG birds having lower activity levels within lightweight birds, but not within heavyweight birds. This study provides indications for activity differences between gait classifications. However, given that there was considerable overlap in activity levels between the gait classifications, future research implementing additional activity-related variables is required to allow a more complete distinction between birds with different gait classifications.

Assessing the Activity of Individual Group-Housed Broilers Throughout Life using a Passive Radio Frequency Identification System-A Validation Study.

Individual data are valuable for assessing the health, welfare and performance of broilers. In particular, data on the first few days of life are needed to study the predictive value of traits recorded early in life for later life performance. However, broilers are generally kept in groups, which hampers individual identification and monitoring of animals. Sensor technologies may aid in identifying and monitoring individual animals. In this study, a passive radio frequency identification (RFID) system was implemented to record broiler activity, in combination with traditional video recordings. The two main objectives were 1) to validate the output of the RFID system by comparing it to the recorded locations on video, and 2) to assess whether the number of antennas visited per unit time could serve as a measure of activity, by comparing it to the distance recorded on video and to the distance moved as recorded using a validated ultra-wideband (UWB) tracking system. The locations recorded by the RFID system exactly matched the video in 62.5% of the cases, and in 99.2% of the cases when allowing for a deviation of one antenna grid cell. There were moderately strong Spearman rank correlations between the distance recorded with the RFID system and the distance recorded from video (rs = 0.82) and between UWB and RFID (rs = 0.70) in approximately one-hour recordings, indicating that the RFID system can adequately track relative individual broiler activity, i.e., the activity level of a broiler in comparison to its group members. As the RFID tags are small and lightweight, the RFID system is well suited for monitoring the individual activity of group-housed broilers throughout life.

Validation of an Ultra-Wideband Tracking System for Recording Individual Levels of Activity in Broilers.

Individual data on activity of broilers is valuable, as activity may serve as a proxy for multiple health, welfare and performance indicators. However, broilers are often kept in large groups, which makes it difficult to identify and monitor them individually. Sensor technologies might offer solutions. Here, an ultra-wideband (UWB) tracking system was implemented with the goal of validating this system for individual tracking of activity of group-housed broilers. The implemented approaches were (1) a comparison of distances moved as recorded by the UWB system and on video and (2) a study recording individual levels of activity of broilers and assessing group-level trends in activity over time; that could be compared to activity trends from literature. There was a moderately strong positive correlation between the UWB system and video tracking. Using the UWB system, we detected reductions in activity over time and we found that lightweight birds were on average more active than heavier birds. Both findings match with reports in literature. Overall, the UWB system appears well-suited for activity monitoring in broilers, when the settings are kept the same for all individuals. The longitudinal information on differences in activity can potentially be used as proxy for health, welfare and performance; but further research into individual patterns in activity is required.

Challenges and priorities for modelling livestock health and pathogens in the context of climate change.

Climate change has the potential to impair livestock health, with consequences for animal welfare, productivity, greenhouse gas emissions, and human livelihoods and health. Modelling has an important role in assessing the impacts of climate change on livestock systems and the efficacy of potential adaptation strategies, to support decision making for more efficient, resilient and sustainable production. However, a coherent set of challenges and research priorities for modelling livestock health and pathogens under climate change has not previously been available. To identify such challenges and priorities, researchers from across Europe were engaged in a horizon-scanning study, involving workshop and questionnaire based exercises and focussed literature reviews. Eighteen key challenges were identified and grouped into six categories based on subject-specific and capacity building requirements. Across a number of challenges, the need for inventories relating model types to different applications (e.g. the pathogen species, region, scale of focus and purpose to which they can be applied) was identified, in order to identify gaps in capability in relation to the impacts of climate change on animal health. The need for collaboration and learning across disciplines was highlighted in several challenges, e.g. to better understand and model complex ecological interactions between pathogens, vectors, wildlife hosts and livestock in the context of climate change. Collaboration between socio-economic and biophysical disciplines was seen as important for better engagement with stakeholders and for improved modelling of the costs and benefits of poor livestock health. The need for more comprehensive validation of empirical relationships, for harmonising terminology and measurements, and for building capacity for under-researched nations, systems and health problems indicated the importance of joined up approaches across nations. The challenges and priorities identified can help focus the development of modelling capacity and future research structures in this vital field. Well-funded networks capable of managing the long-term development of shared resources are required in order to create a cohesive modelling community equipped to tackle the complex challenges of climate change.

Genetic parameters for clinical mastitis in the first three lactations of Dutch Holstein cattle.

The first breeding value for udder health of a bull is based on the performance of his daughters in their first lactation. However, clinical mastitis (CM) is not a problem in first lactation only. Therefore, the objective of this study was to estimate genetic parameters for CM and somatic cell count (SCC) for the first three lactations of Dutch Holstein cattle. Data from 250 Dutch herds recording CM were used to quantify the genetic variation of CM in parity 1, 2, and 3, respectively. The dataset contained 35,379 lactations from 21,064 animals of different parities. Test-day SCC was available from all lactations. Somatic cell counts were log-transformed to somatic cell scores (SCS) and averaged over test-day records between 5 and 335, 5 and 150, and 151 and 335 days in milk. Variance components for CM and SCS were estimated using a sire-maternal grandsire model. The heritability for CM was approximately 3% in all parities. Genetic correlations between CM in consecutive lactations were high (0.9), but somewhat lower between parity 1 and 3 (0.6). All genetic correlations between CM and SCS were positive, implying that genetic selection on lower SCC will reduce CM-incidence. Estimated genetic correlations were stronger for SCS in the first half of lactation than in the second half of lactation. Selection indices showed that most progress could be achieved when treating CM in parity 1, 2, and 3 as different traits and by including SCS between 5 and 150 days in the udder health index.